Application of neural networks to predict the steady state performance of a Run-Around Membrane Energy Exchanger

Modeling the performance characteristics of thermal systems has been a research interest for many decades with moisture transfer systems experiencing a resurgence over the last decade, especially in heating, ventilating, and air conditioning (HVAC) applications. In this study, a neural network (NN) model is developed to predict the heat and moisture transfer performances (i.e., the sensible and latent effectivenesses) of a novel HVAC energy exchanger called the Run-Around Membrane Energy Exchanger (RAMEE) which is able to transfer both heat and moisture between exhaust and supply air streams. The training data set for the NN model covers a wide range of design and operating parameters and is produced using an experimentally validated finite difference (FD) model. Two separate NNs (one for sensible and one for latent energy transfer) each with five inputs and one output, are selected to represent the RAMEE. The results from NN models are numerically and experimentally validated. The root mean squared error (RMSE) between the FD and NN models are 0.05 °C and 2 × 10^?5 kg_v/kg_a, indicating satisfactory agreement for energy exchange calculations. The paper reports the weights and biases to make the results of this study reproducible. These NN models are very fast and easy to use therefore, they might be used for design and for estimating the annual energy savings in different buildings which use the RAMEE in their HVAC system. Additionally, the NN models can be used with optimization algorithms to maximize energy savings and minimize life-cycle costs for a given system.     

Transient behavior of run-around heat and moisture exchanger system. Part І: Model formulation and verification

In Part І, a numerical model for coupled heat and moisture transfer in a run-around heat and moisture exchanger with a liquid desiccant coupling fluid is developed. The numerical model is two dimensional, transient and is formulated using the finite difference method with an implicit time discretization. The results from the numerical model for the case of only heat transfer for a single heat exchanger are compared to an available analytical solution and good agreement is obtained. For the simultaneous heat and moisture transfer in the run-around membrane energy exchanger (RAMEE), a comparison between numerical model results and experimental measurements obtained from laboratory testing for both sensible and latent effectiveness showed satisfactory agreement at different operating conditions. Part II of this paper applies the model for a range of initial conditions [32].     

Steady-state performance of a run-around membrane energy exchanger (RAMEE) for a range of outdoor air conditions

The steady-state performance of a run-around membrane energy exchanger (RAMEE) for a wide range of outdoor air conditions is presented here. The RAMEE is numerically simulated and the sensible and latent effectiveness values corresponding to the maximum total energy effectiveness for different outdoor air conditions are presented. The effectiveness values are shown to be very dependent on outdoor conditions which results in some effectiveness values exceeding 100% or being less than 0% for several of the outdoor air conditions investigated. The heat and moisture transfers are shown to influence the latent and sensible performances of the RAMEE, respectively.     

Modeling of Air to Air Enthalpy Heat Exchanger

The thermal performance of a Z-shaped enthalpy heat exchanger utilizing 45-gsm Kraft paper as the heat and moisture transfer surface for heating, ventilation, and air conditioning (HVAC) energy recovery is experimentally investigated through temperature and moisture content measurements. A mathematical model is developed and validated against the experimental results using the effectiveness-NTU method. In this model the paper moisture transfer resistance is determined by paper moisture permeability measurements. Results showed that the paper moisture transfer resistance is not constant and varies with moisture gradient across the paper. Furthermore, the model is used to predict the heat exchanger performance for different heat exchanger flow configurations. The results showed that higher effectiveness values are achieved when the heat exchanger flow path width is reduced. Temperature and moisture distribution in the heat exchanger is also studied using a computational fluid dynamics package (FLUENT). To model the moisture transfer through the porous materials a nondimensional sensible–latent effectiveness ratio was developed to obtain the moisture boundary conditions on the heat exchanger surface.     

Transient behavior of run-around heat and moisture exchanger system. Part IІ: Sensitivity studies for a range of initial conditions

Part І of this paper [17] developed and verified the numerical model for simultaneous heat and moisture transfer in the run-around membrane energy exchanger (RAMEE) system to determine the transient behavior of the system under different initial and operating conditions.This paper presents the transient response of the RAMEE system for step changes in the inlet supply air temperature and humidity ratio. Also the system quasi-steady state operating conditions are predicted as the system approaches its asymptotic operating condition. The transient responses are predicted with changes in various parameters. These include: the number of heat transfer units, thermal capacity ratio, heat loss/gain ratio, storage volume ratio and the normalized initial salt solution concentration. It is shown that the storage volume ratio and the initial salt solution concentration have significant impacts on the transient response of the system and heat transfer between the RAMEE system and the surrounding environment can change the system quasi-steady conditions substantially.     

Weather data for building energy cost-benefit analysis

This paper deals with European TRY weather data processing for climatic indexes generation, useful for HVAC energy and cost simplified evaluation. For nine Italian locations are presented: 99 and 2·5% dry bulb temperatures, 2·5% wet bulb temperatures, heating and cooling degree days, latent enthalpy days, unitary sensible and latent loads. TRY psychrometric data were processed according to a bin method that preserves the correlation between dry bulb temperature and moisture content, and then reduced by an averaging technique. An example is worked out in order to present an engineering shorthand for energy and cost evaluation of HVAC system. © 1998 John Wiley & Sons, Ltd.     

Modeling of heat and moisture transport by periodic ventilation of thin cotton fibrous media

In walking conditions, the air spacing between the fabric layer of a porous clothing system and the human skin changes with the walking frequency. This change will cause air penetration in and out of the clothing system depending on the fabric air permeability. The air passing through the fabric can considerably reduce the heat and moisture transfer resistance of the clothing system and its suitability for a given thermal environment. In this work, the coupled convection heat and moisture exchange within the clothing system subject to sinusoidal air layer thickness variation about a fixed mean is experimentally investigated and theoretically modeled to predict the periodic fabric regain, the fabric temperature and the transient conditions of the air layer located between the fabric and the skin.Experiments were conducted in environmental chambers under controlled conditions using a sweating hot plate at 35 °C that represents the human skin and a gear motor to generate the oscillating fabric motion. The first set of experiments was done using a dry isothermal hot plate to measure the sensible heat transfer. The second set of experiments was conducted with an isothermal sweating hot plate and the total heat (sensible and latent) transport from the plate was recorded.A mathematical model was developed for the heat and mass transport through the air spacing layer and the fiber clothing system. In the fabric, a three-node adsorption model was used to describe the effect of fabric motion (ventilation) on the sensible and latent heat flows from the human skin under different environmental conditions. The fiber model was linked to the transport model of the oscillating air spacing layer that falls between the fiber and the fixed boundary (human skin). The transport equations were solved numerically. The sensible and latent heat transport quantities at the moist solid boundary were calculated. A reasonable agreement was observed between the model predictions of heat loss or gain from the hot plate and the experimentally measured results.     

Virtual models of indoor-air-quality sensors

A data-driven approach for modeling indoor-air-quality (IAQ) sensors used in heating, ventilation, and air conditioning (HVAC) systems is presented. The IAQ sensors considered in the paper measure three basic parameters, temperature, CO₂, and relative humidity. Three models predicting values of IAQ parameters are built with various data mining algorithms. Four data mining algorithms have been tested on the HVAC data set collected at an office-type facility. The computational results produced by models built with different data mining algorithms are discussed. The neural network (NN) with multi-layer perceptron (MLP) algorithms produced the best results for all three IAQ sensors among all algorithms tested. The models built with data mining algorithms can serve as virtual IAQ sensors in buildings and be used for on-line monitoring and calibration of the IAQ sensors. The approach presented in this paper can be applied to HVAC systems in buildings beyond the type considered in this paper.     

Physical mechanisms of heat transfer during single bubble nucleate boiling of FC-72 under saturation conditions. II: Theoretical analysis

This paper is the second part of a two-part study concerning the dynamics of heat transfer during the nucleation process of FC-72 liquid. The experimental findings on the nature of different heat transfer mechanisms involved in the nucleation process were discussed in part I. In this paper, the experimental results are compared with the existing boiling models. The boiling models based on dominance of a single mechanism of heat transfer did not match the experimental results. However, the Rohsenow model was found to closely predict the heat transfer through the microconvection mechanism that is primarily active outside the bubble/surface contact area. An existing transient conduction model was modified to predict the surface heat transfer during the rewetting process (i.e. transient conduction mechanism). This model takes into account the gradual rewetting of the surface during the transient conduction process rather than a simple sudden surface coverage assumption commonly used in the boiling literature. The initial superheat energy of the microlayer (i.e. microlayer sensible energy) was accurately calculated and found to significantly contribute in microlayer evaporation. This even exceeded the direct wall heat transfer to microlayer at high surface superheat temperatures. A composite model was introduced that closely matches our experimental results. It incorporates models for three mechanisms of heat transfer including microlayer evaporation, transient conduction, microconvection, as well as their influence area and activation time. The significance of this development is that, for the first time, all submodels of the composite correlation were independently verified using experimental results.     

A Comparison Study of Sensible and Latent Thermal Energy Storage Systems for Concentrating Solar Power Applications

Thermal energy storage (TES) provides a key opportunity to reduce the cost of concentrating solar power generation. In this article transient heat transfer performance and operational characteristics of sensible TES systems (made of liquid solar salt) and latent TES systems (made of sodium nitrate undergoing liquid-solid phase change), all enclosed in vertical annuli, are numerically simulated. The results show that the latent TES systems can operate with a much higher energy density than the sensible TES systems, and that compact latent TES systems are capable of offering both high energy density and a satisfactory charging/discharging rate.     

Optimization of an HVAC system with a strength multi-objective particle-swarm algorithm

A data-driven approach for the optimization of a heating, ventilation, and air conditioning (HVAC) system in an office building is presented. A neural network (NN) algorithm is used to build a predictive model since it outperformed five other algorithms investigated in this paper. The NN-derived predictive model is then optimized with a strength multi-objective particle-swarm optimization (S-MOPSO) algorithm. The relationship between energy consumption and thermal comfort measured with temperature and humidity is discussed. The control settings derived from optimization of the model minimize energy consumption while maintaining thermal comfort at an acceptable level. The solutions derived by the S-MOPSO algorithm point to a large number of control alternatives for an HVAC system, representing a range of trade-offs between thermal comfort and energy consumption.     

Modeling of heat transfer and energy analysis of potato slices and cylinders during solar drying

In the present work, a method based on energy balance considering the effects of heat capacity of the food product, radiative heat transfer from food product to the drying chamber and solar radiation absorbed in the product during drying is proposed for determination of convective heat transfer coefficient, h_c. A natural convection mixed-mode solar dryer is used for performing the experiments on potato cylinders and slices of same thickness of 0.01 m with respective length and diameter of 0.05 m. The present investigation indicates that the cylindrical samples exhibit higher values of h_c and faster drying rate compared to those of slices, as expected. The h_c values for each sample shape are correlated by an equation of the form Nu = C(Ra)ⁿ. Laplace transform is applied to solve the proposed heat transfer diffusion model considering the effect of moisture transfer rate to predict the transient sample temperature. The model is validated through a close agreement between calculated and experimental results of transient sample temperature. Results of energy analysis reveal that for both the sample geometries, decreasing product moisture content during drying resulted in significant reduction in specific energy consumption. For almost similar drying conditions, a considerable amount of reduction in specific energy consumption is achieved for cylinders, as expected.     

HVAC领域相变贮能研究的现状与进展

总结了相变传热的特点及求解方法 ;相变墙板的研制以及使用效果方面的研究现状 ;相变在供暖、空调系统中的应用 ;相变贮能技术在HVAC中应用的诸多优势。提出了HVAC领域相变贮能技术今后的研究方向。     

Performance Deteriorations from Flow Maldistribution in Air-to-Air Heat Exchangers: A Parallel-Plates Membrane Core Case

Parallel-plates membrane cores have been widely used in air-to-air heat exchangers for fresh air heat and moisture recovery, which are also called total heat exchangers. Flow maldistribution and the consequent performance deteriorations are of great interest. The flow maldistribution is predicted with a CFD code, by treating the parallel-plates core as a two-dimensional porous media. Then, a coupled heat and moisture transfer model between the two air flows in the parallel-plates channels is set up. Using the CFD predicted flow distribution data on core face, the sensible heat and moisture exchange effectiveness and the performance deterioration factors are calculated with finite-difference scheme. Experiments are performed to validate the heat mass transfer model. The results indicate that for the current structure, when the channel pitch is below 2.0 mm, the flow distribution is quite homogeneous and the sensible and latent performance deteriorations due to flow maldistribution are below 9% and can be neglected. However, when the channel pitch is larger than 2 mm, the maldistribution is quite large and the consequent thermal and latent performance can be deteriorated by 28%. The flow maldistribution the consequent thermal and latent effectiveness deteriorations for parallel-plates cores are more serious than those for plate-fin cores previously reported.     

Effectiveness of energy wheels from transient measurements: Part II—Results and verification

This paper verifies the accuracy of a new transient test method for air-to-air energy wheels. To accomplish this, the transient characteristics of several energy wheels exposed to separate and independent step changes in humidity and temperature are measured. These characteristics are then used to predict the effectiveness of the wheels using the effectiveness model presented in Part I of this paper [O.O. Abe, C.J. Simonson, R.W. Besant and W. Shang, Effectiveness of energy wheels from transient measurements: Part I—Prediction of effectiveness and uncertainty, Int. J. Heat Mass Transfer, accepted for publication. [1]]. Comparison of the predicted latent and sensible effectiveness with experimental standard test data (steady state) show agreement within uncertainty bounds. Comparison with numerical simulations results also show agreement within the uncertainty bounds except for the special case of very low face velocity entering the energy wheels.     

Heat and mass transfer in plate-fin enthalpy exchangers with different plate and fin materials

Enthalpy exchangers have been used as an efficient means to recover both sensible heat and moisture from exhaust ventilation air. A cross-flow plate-fin structure is the most popular arrangement for the exchanger core due to its compactness and high mechanical strength even with very small channel wall thickness. Traditionally, hygroscopic paper is selected as the plate and fin materials. Though the sensible effectiveness with this material is satisfactorily high, the latent effectiveness is disappointingly low due to the low moisture diffusivity in paper. To solve this problem, in this study, a novel concept is proposed to augment moisture transfer in the exchanger. Plates and fins are made with different materials. A novel membrane – the composite supported liquid membrane (CSLM) is used as the plate material. Paper is still used as the fin material for its cheapness and high support strength. To make comparisons, two cores, one is paper-fin and paper-plate, and another one is paper-fin and membrane-plate, are constructed and tested for heat and moisture recovery. Simultaneous heat and moisture transfer in the plate-fin core is studied. Mathematical model governing the heat and moisture transfer in the cores is set up and numerically solved. Both the experimental data and numerical results indicate that the latent effectiveness of the paper-fin and membrane-plate core is 60% higher than the traditional paper-fin and paper-plate core, due to the high moisture diffusivity in the CSLM.     

Thermal characterization of phase change materials based on linear low-density polyethylene,paraffin wax and expanded graphite

Thermal characterization of Phase Change Materials (PCMs) based on linear low-density polyethylene (LLDPE), paraffin wax (W) and expanded graphite (EG) is reported in this paper. Investigated PCMs showed high potential for application in energy storage systems.The latent heat, L_m, sensible heat Q_sens, and the ability of the prepared PCMs to store and release thermal energy were investigated using specific home-made equipment based on the transient guarded hot plane method (TGHPT). The sensible heat of PCM containing 40 wt.% of paraffin wax was investigated in the temperature range 25–35 °C, they exhibited a drop in Q_sens from 31 to 24 J/g depending on the concentration of EG. A similar decrease in sensible heat with increased loading of EG was observed for PCMs containing 50 wt.% of EG.The storage and release of thermal energy during phase change which is associated with the latent heat of the materials were investigated within the temperature range 20–50 °C. PCMs containing 40 wt.% of paraffin wax exhibited latent heat of 36 J/g, whereas the latent heat of PCMs containing 50 wt.% of paraffin wax was 49 J/g. The addition of EG decreased the time needed to melt and solidify PCMs due to increase in thermal conductivity of PCMs with increase in EG content. This behavior was confirmed by the thermal conductivity measurements, where thermal conductivity increased from 0.252 for sample without EG to 1.329 W/m × °C for PCM containing 15 wt.% of EG.The reproducibility of storage and release of thermal energy by PCMs was demonstrated by subjecting them to repeated heating and cooling cycles (over 150 cycles).     

Comparison of neural network,conditional demand analysis,and engineering approaches for modeling end-use energy consumption in the residential sector

This paper investigates the use of conditional demand analysis (CDA) method to model the residential end-use energy consumption at the national level. There are several studies where CDA was used to model energy consumption at the regional level; however the CDA method had not been used to model residential energy consumption at the national level. The prediction performance and the ability to characterize the residential end-use energy consumption of the CDA model are compared with those of a neural network (NN) and an engineering based model developed earlier. The comparison of the predictions of the models indicates that CDA is capable of accurately predicting the energy consumption in the residential sector as well as the other two models. The effects of socio-economic factors are estimated using the NN and the CDA models, where possible. Due to the limited number of variables the CDA model can accommodate, its capability to evaluate these effects is found to be lower than the NN model.     

A novel predictive architecture for microwave-assisted drying processes based on neural networks

In this contribution, a novel learning architecture based on the interconnection of two different learning-based neural networks has been used to both predict temperature and drying curves and solve inverse modelling equations in microwave-assisted drying processes. In this way, a neural model that combines the accuracy of neural networks based on Radial Basis Functions (RBF) and the algebraic capabilities of the matrix polynomial structures is presented and validated. The architecture has been trained by temperature (T_c(t)) and moisture content (X_t(t)) curves, which have been generated by a previously validated drying model. The results show that the neural model is able to very accurately predict both kind of curves for any combination of the considered input variables (electric field and air temperature) provided that an appropriate training process is performed. The proposed configuration also permits the solution of the inverse problem in the drying process by finding the optimal value for the electric field. This provides T_c(t) or X_t(t) curves that fit to a desired drying condition in a specific time slot.     

Identification of temperature and moisture content fields using a combined neural network and clustering method approach

Studies on the dynamics of temperature and moisture content distributions in porous soils have provided important insight on their effect on the building hygrothermal behavior, where the interaction between both building and soil can contribute to reduce building thermal gains or looses. Hygrothermal aspects can be related to many attributes such as energy consumption, occupants' thermal comfort and health, and material deterioration. Recently, a great variety of mathematical models to predict thermal and moisture content profiles in porous media have been presented in the literature. Most of those models are based on analysis of multilayer measurements or on Fourier analysis. The development and validation of such mathematical models facilitate the understanding of heat and moisture flows at different soil depths. In this research, a radial basis function neural network (RBF-NN) approach, combined with Gath–Geva clustering method in order to predict the temperature and moisture content profiles in soils, has been presented. A set of data obtained from the computation of the coupled heat and moisture transfer in porous soils for the Curitiba city (Paraná State, Brazil) weather data file has been used by the RBF-NN modeling method. Simulation results indicate the potentialities of the RBF-NNs to learn, for the one step ahead identification, the behavior of temperature and moisture content profiles in the media at various depths.